Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natural language processing, it is sure that now is a time of either using a Transformer-like model or hybrid CNNs with attention. However, the former need a tremendous resource to train, and the latter is in the perfect balance in this direction. In this work, to make CNNs handle global and local information, we proposed UPANets, which equips channel-wise attention with a hybrid skip-densely-connection structure. Also, the extreme-connection structure makes UPANets robust with a smoother loss landscape. In experiments, UPANets surpassed most well-known and widely-used SOTAs with an accuracy of 96.47% in Cifar-10, 80.29% in Cifar-100, and 67.67% in Tiny Imagenet. Most importantly, these performances have high parameters efficiency and only trained in one customer-based GPU. We share implementing code of UPANets in https://github.com/hanktseng131415go/UPANets.
Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels
The University of Manchester（曼彻斯特大学）；Kaohsiung Chang Gung Memorial Hospital（高雄长庚纪念医院）；Chang Gung University College of Medicine（长庚大学医学院）；Cheng Shiu University（正修科技大学）；National Yang Ming Chiao Tung University（国立阳明交通大学）；The Hong Kong University of Science and Technology（香港科技大学）
Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse annotations (tags, boxes) lack precise pixel localization whereas sparse annotations (points, scribbles) lack broad region coverage. Existing methods tackle these two types of weak supervision differently: Class activation maps are used to localize coarse labels and iteratively refine the segmentation model, whereas conditional random fields are used to pro…
Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation
School of Biomedical Engineering, Division of Life Sciences；Medicine, University of Science；Technology of China (USTC), Hefei, Anhui 230026, China Center for Medical Imaging, Robotics, Analytic Computing \& Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, Jiangsu 215123, China Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology, Suzhou Jiangsu, 215123, China State Key Laboratory of Precision
IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation
Zhejiang University（浙江大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Ningbo Global Innovation Center, Zhejiang University（浙江大学宁波全球创新中心）；Zhejiang Key Laboratory of Digital-Intelligence Service Technology（浙江省数字智能服务技术重点实验室）
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；PCL Research Center of Networks and Communications, Peng Cheng Laboratory（鹏城实验室网络通信PCL研究中心）
Recently, deep neural networks (DNNs) have been widely and successfully used in Object Detection, e.g. Faster RCNN, YOLO, CenterNet. However, recent studies have shown that DNNs are vulnerable to adversarial attacks. Adversarial attacks against object detection can be divided into two categories, whole-pixel attacks and patch attacks. While these attacks add perturbations to a large number of pixels in images, we proposed a diffused patch attack (\textbf{DPAttack}) to successfully fool object detectors by diffused patches of asteroid-shaped or grid-shape, which only change a small number of pi…
Single Image Inpainting and Super-Resolution with Simultaneous Uncertainty Guarantees by Universal Reproducing Kernels
Institute for Computer Science and Control (SZTAKI)（计算机科学与控制研究所）；Institute of Mathematics, Budapest University of Technology and Economics (BME)（布达佩斯技术大学数学研究所）
Pruning well-trained neural networks is effective to achieve a promising accuracy-efficiency trade-off in computer vision regimes. However, most of existing pruning algorithms only focus on the classification task defined on the source domain. Different from the strong transferability of the original model, a pruned network is hard to transfer to complicated downstream tasks such as object detection arXiv:arch-ive/2012.04643. In this paper, we show that the image-level pretrain task is not capable of pruning models for diverse downstream tasks. To mitigate this problem, we introduce image reco…
Establishing dense correspondences between a pair of images is an important and general problem, covering geometric matching, optical flow and semantic correspondences. While these applications share fundamental challenges, such as large displacements, pixel-accuracy, and appearance changes, they are currently addressed with specialized network architectures, designed for only one particular task. This severely limits the generalization capabilities of such networks to new scenarios, where e.g. robustness to larger displacements or higher accuracy is required. In this work, we propose a univer…
SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos
Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong, China（人工智能与机器人中心，香港科学与创新研究院，中国科学院，香港，中国）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院，北京，中国）；Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany（医学辅助程序，慕尼黑技术大学，德国慕尼黑）；Electronic Engineering Department, The Chinese University of Hong Kong, Hong Kong, China（电子工程系，香港中文大学，香港，中国）；Neuromedical Centre, Hong Kong University Shenzhen Hospital, Shenzhen, China（神经医学中心，香港大学深圳医院，深圳，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）；Department of Respiratory Medicine, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China（呼吸科，中山大学附属第一医院，广州，中国）
Object movement identification is one of the most researched problems in the field of computer vision. In this task, we try to classify a pixel as foreground or background. Even though numerous traditional machine learning and deep learning methods already exist for this problem, the two major issues with most of them are the need for large amounts of ground truth data and their inferior performance on unseen videos. Since every pixel of every frame has to be labeled, acquiring large amounts of data for these techniques gets rather expensive. Recently, Zhao et al. [1] proposed one of a kind Ar…
This paper tackles a new photometric stereo task, named universal photometric stereo. Unlike existing tasks that assumed specific physical lighting models; hence, drastically limited their usability, a solution algorithm of this task is supposed to work for objects with diverse shapes and materials under arbitrary lighting variations without assuming any specific models. To solve this extremely challenging task, we present a purely data-driven method, which eliminates the prior assumption of lighting by replacing the recovery of physical lighting parameters with the extraction of the generic l…
PAII Inc.（PAII公司）；Ping An Technology（平安科技）；Beijing United Family Hospital（北京和睦家医院）；Chang Gung Memorial Hospital（长庚纪念医院）
Accurately segmenting a variety of clinically significant lesions from whole body computed tomography (CT) scans is a critical task on precision oncology imaging, denoted as universal lesion segmentation (ULS). Manual annotation is the current clinical practice, being highly time-consuming and inconsistent on tumor's longitudinal assessment. Effectively training an automatic segmentation model is desirable but relies heavily on a large number of pixel-wise labelled data. Existing weakly-supervised segmentation approaches often struggle with regions nearby the lesion boundaries. In this paper, …
Facebook AI Research (FAIR)（脸书人工智能研究院）；University of Illinois at Urbana-Champaign (UIUC)（伊利诺伊大学厄巴纳-香槟分校）
Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing specialized architectures for each task. We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). Its key components include masked attention, which extracts localized features by constraining cross-attention within predicted mask regions. In addition to…
Throughout the evolution of the neural networks more specialized cells were added to the set of basic building blocks. These cells aim to improve training convergence, increase the overall performance, and reduce the number of required labels, all while preserving the expressive power of the universal network. Inspired by the partitioning of the human visual perception system between the eyes and the cerebral cortex, we present TPNET, which offloads universal and application-specific CNN from the bulk processing of the high resolution pixel data and performs the translation-variant image corre…
EAPCR: A Universal Feature Extractor for Scientific Data without Explicit Feature Relation Patterns
Dali University（大理大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Stony Brook University（石溪大学）；Rutgers University（罗格斯大学）；Chinese Academy of Sciences（中国科学院）
Tianjin University（天津大学）；Institute of High Performance Computing, A*STAR（A*STAR高性能计算研究所）；Imperial College London（帝国理工学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
In recent years, Denoising Diffusion Models have demonstrated remarkable success in generating semantically valuable pixel-wise representations for image generative modeling. In this study, we propose a novel end-to-end framework, called Diff-UNet, for medical volumetric segmentation. Our approach integrates the diffusion model into a standard U-shaped architecture to extract semantic information from the input volume effectively, resulting in excellent pixel-level representations for medical volumetric segmentation. To enhance the robustness of the diffusion model's prediction results, we als…
